Artificial Intelligence-Based Approach for Chronic Kidney Disease Detection

Document Type

Article

Publication Title

Asean Journal of Scientific and Technological Reports

Abstract

Chronic Kidney Disease (CKD) is a long-term medical condition in which the kidneys gradually lose their ability to function properly. Early detection of CKD is crucial for preventing severe complications and improving patient outcomes. Traditionally, CKD diagnosis has relied on manual analysis of clinical parameters and laboratory tests, which often lack scalability and precision. Artificial Intelligence (AI), through machine learning algorithms, has transformed healthcare by enabling automated and accurate disease detection. Datasets play a pivotal role in developing AI-based diagnostic systems, as the quality and balance of data significantly influence model performance. The majority of existing research on CKD detection has focused on balanced datasets, where data samples are evenly distributed across classes, to recommend the most effective classifiers for detection. However, in real-world scenarios, datasets are often imbalanced, with minority classes underrepresented, leading to biased models and poor detection of critical cases. Therefore, adopting suitable techniques to handle these imbalances is necessary. In this context, this paper addresses the issue by evaluating the performance of various classifiers on both slightly imbalanced and severely imbalanced CKD datasets. Through comprehensive experimentation, the research identifies that Gradient Boosting Machine (GBM) demonstrates robust performance across both slightly and severely imbalanced datasets by achieving 99.25% ± 0.68 and 92.26% ± 2.23 testing accuracy, 100% and 90.79% ±3.9 AUROC, 0.01 ± 0.01 and 0.39 ± 0.15 LR-, 64.98% and 84.54% ±3.41 H-measure. This work emphasizes the need for adaptable classifiers that reflect real-world data, improving the reliability of AI-based CKD diagnosis.

DOI

10.55164/ajstr.v28i5.258012

Publication Date

9-1-2025

This document is currently not available here.

Share

COinS